 |
|
|
|
|
Products & Solutions / By Solution / Forecaster XL / FAQ |
|||||
For customer acquisition, risk mitigation, customer management and fraud prevention solutions we recommend our strategic partner - Scorto Corp.
|
General Where can I get additional information about neural networks? How could I improve things to get better forecasting? When neural networks are a bad choice for my forecasting? Data Analysis and Preprocessing How much historical data do I need? What is a categorical column? Why Forecaster XL ignored some rows and columns? Network Preparation What is network training? What training algorithm Forecaster XL uses? How Forecaster XL determines neural network topology suitable for my problem? Why I cannot see MSE and absolute error in the network training report? What is “error change” in stopping conditions? How much time is required for network training? General Where can I get additional information about neural networks? There is a good introductory book written by Kevin Gurney and available online at: http://www.shef.ac.uk/psychology/gurney/notes/index.html You can also try Dr. Leslie Smith’s brief online introduction to neural networks packed with pictures and examples at: http://www.cs.stir.ac.uk/~lss/NNIntro/InvSlides.html. A good introductory book for managers and business analysts is: For engineers and technically-minded people we’d recommend to start with: Fausett, L. (1994), Fundamentals of Neural Networks: Architectures, Algorithms, and Applications, Englewood Cliffs, NJ: Prentice Hall. For financial specialists, bankers and traders we recommend starting with: E. Michael Azoff (1994). Neural Network Time Series: Forecasting of Financial Markets NY: John Wiley and Sons, Inc. How could I improve things to get better
forecasting?
 top
Data Analysis and Preprocessing How much historical data do I need? You definitely need to have more records in the training subset than the total number of input columns. The number of records needed for training depends on the complexity of your problem and amount of noise in your data. There are no exact rules. Typically, it’s recommended to have at least 10 times as many records for training as input columns. This may not be enough for problems with subtle and complex dependencies in data. Try to add more data if your network has poor results. What is a categorical column? Each value of a categorical column represents a certain category. For example, categorical is a column that contains only “Male” or “Female” as its values. Typically, the number of different values in a categorical column is much less than the number of records. Categorical data should be encoded in a special way to be suitable for a neural network. You may manually mark a column as categorical in Expert Mode (using Details button at Data Analysis Progress step). This feature may be beneficial for some cases. For example, your data has a column “Model” that has values “1”, “2”, “3”. By default, this column will be considered as a numeric, but it will be more beneficial to encode it as a categorical one. Why Forecaster XL ignored some rows and columns? This may happen if some of your columns or rows are unsuitable for neural network. For example, text or data/time data cannot be processed by neural network. Also, some your rows may have missing or invalid data; such rows will be ignored. To see which columns and rows were ignored look into Data Preprocessing Report. top
Network Preparation What is network training? Network training means adjusting neural network weights. During training the network analyzes the data you have provided and changes weights between network units to reflect dependencies found in your data. What training algorithm Forecaster XL uses? Forecaster XL uses constructive algorithm to train network and select the network topology. This constructive algorithm is developed by Alyuda's Research Group and is capable of automatic selection and tuning of training parameters and network topology. How Forecaster XL determines neural network topology suitable for my problem? See What training algorithm Forecaster XL uses? What stopping conditions should I specify to improve forecasting quality? As the first step we recommend you using default settings that means your network is trained until error reduction is no longer possible. If forecasting error is still unacceptably high we recommend reducing MSE value, reducing the error change value and increasing number of iterations. Why I cannot see MSE and absolute error in the network training report? When your target column is not numeric, it is hard to define unambiguously what the absolute error is. For such cases it is better to use correct classification rate to let you know what percentage of data was recognized correctly. What is “error change” in stopping conditions? Error change specifies the error change during several last iterations. This parameter is useful for detection of situations when each new iteration has almost no influence on error and thus the network cannot further improve its performance and training should be stopped to save time. Although one should be careful with this parameter because in certain cases the error can be decreased after a lot of “motionless” iterations. It's impossible to automatically detect such cases. We recommend setting 10 iterations, which is enough for most of problems. For certainty you can set up to 100 iterations. How much time is required for network training? The time required for network training depends on the number of inputs, number of hidden units, amount of data, complexity of the task and capability of your computer. Complete network training can continue from several seconds to several hours. top
|
||||